UCS633 Project Submission

• Name - Kartikey Tiwari
• Roll no. - 101703282

kt-toposis

kt-toposis is a Python package for displaying ranking of all criteria using Topsis technique to get good computational efficiency and ability to measure the relative performance for each alternative in a simple mathematical form.

Topsis Description

Technique for Order Preference by Similarity to an Ideal Solution (TOPSIS) is one of the multi-criteria models in making decision which is known for its simplicity, rationality, comprehensibility and good computational efficiency. Multi-criteria decision making (MCDM) refers to making choice of the best alternative from among a finite set of decision alternatives in terms of multiple, usually conflicting criteria.

Getting Started

These instructions will help you to install and use this package for general use.

Prerequisites

Your csv file should not have categorical data

Installation

Use the package manager pip to install foobar.

pip install kt-toposis

Usage

You can import it either in Python IDLE or run directly through command prompt

For Command Prompt

If you want to use this package on "data.csv" file with 4 columns. You need to change the directory where "data.csv" is stored then. Here -w represents weights which signifies weight of each feature or column in our dataset and -i represents impacts which signifies impact of each column or feature in our data. If a feature is good we will use + to denote else we will use -

kt-toposis data.csv -w 1 1 1 1 -i + + - +

You can use the following command for help

kt-toposis -h

For Python IDLE

from kt_toposis.topsis import top
top(X,weights,impacts)

#X should be a matrix
#impacts should be a list of string + for positive impact - for negative impact
#weights should be a list of int or float

Sample dataset

kt-toposis Book1.csv -w 1 1 1 1 1 -i + + + + +

Result

  Topsis Selection
Models     | Rank
-----------------------
1          | 3
2          | 5
3          | 4
4          | 1
5          | 2
Successfully executed

Contributing

Pull requests are welcome. For major changes, please open an issue first to discuss what you would like to change.

Please make sure to update tests as appropriate.

License

MIT